Set up Cline / Roo Code
Open-source coding agents in VS Code. Choose "OpenAI Compatible" and fill in three fields
- API format: OpenAI Chat Completions
- Base URL format: Up to /v1 (https://gpt.cherrychat.org/v1)
- Recommended model: claude-sonnet-5-5, gpt-6.1-sol
- Platforms: VS Code
Steps
Install the extension
Search the VS Code Extensions view for "Cline" or "Roo Code" and install it. They are separate extensions with separate settings; configure the one you use.
Open the settings
Cline: click the Cline icon in the activity bar, then the gear ⚙️ at the top right of the panel. Roo Code: click the Roo Code icon, then the gear to reach its provider settings.
Choose OpenAI Compatible and fill in
Set API Provider to "OpenAI Compatible", then fill in the three fields below.
- Base URL: https://gpt.cherrychat.org/v1 (End at /v1, without /chat/completions)
- API Key: sk-your-key
- Model ID: claude-sonnet-5-5
Adjust Model Configuration
Expand Model Configuration: set Context Window from the Models page and Max Output Tokens to about 8192; enable Image Support only for vision models. Leave "Use Azure Identity Authentication" (Cline) and other Azure options unticked. If Cline shows a Verify button, click it.
Try it
Send "list the files in the current folder"; when it starts calling tools, you are connected.
Common pitfalls
- Base URL must be https://gpt.cherrychat.org/v1: not https://gpt.cherrychat.org/v1/chat/completions, and not the leftover https://api.openai.com/v1.
- Roo Code relies on native tool calling only, so pick a model that supports it (Claude and GPT models do).
- Model ID must match the Models page exactly (all lowercase); even a stray space causes "model not found".
- Coding agents send many requests per task and use lots of tokens; consider setting a spending cap on the key under My Keys.
Error → cause → fix
| What you see | Why | What to do |
|---|---|---|
| Invalid API Key / 401 | The key is wrong, has spaces, or was disabled | Copy the key again from My Keys and paste it |
| 404 / Connection Error | Base URL is missing /v1 or includes /chat/completions | Change it to https://gpt.cherrychat.org/v1 |
| Model Not Found | Model ID is misspelled (case or spaces) | Copy it from the Models page, e.g. claude-sonnet-5-5 |
| Chat works but tool calls fail | The chosen model does not support tool calling | Switch to claude-sonnet-5-5 or gpt-6.1-sol |
| HTTP 402 or "insufficient balance" (billing_error in Claude format) | Your credits cannot cover this call. API calls are paid from credits only; memberships and unlimited plans do not apply | Top up any amount in the CherryChat Store, then retry after a few seconds |
| HTTP 429 Too Many Requests | Too many requests: by default 120 per minute per key and 8 at a time per account | Lower the concurrency or requests per second in the tool and wait for the Retry-After seconds; most tools retry on their own |
Guide checked 2026-11-02. The tool's screens may change; the official docs win if they differ.
Operated by UK Company CHERRYCHAT LTD · Company Number 16096119 · Support WeChat: JsnonoChat · Content is AI-generated — please verify before relying on it
